© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9616
    Prev
    Next
    INDEX
    Explanations

    collagen, elastin, hyaluronic acid, keratin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     三角
    0.43
    ąc
    0.41
     Sep
    0.39
    涉
    0.39
     sep
    0.39
     relocate
    0.38
    钲
    0.38
    舒
    0.38
    
    0.38
     relocation
    0.37
    POSITIVE LOGITS
     keratin
    0.76
    Ker
    0.63
     Ker
    0.61
     elastin
    0.60
     collagen
    0.58
    ker
    0.57
     Collagen
    0.56
     kerat
    0.54
     ker
    0.53
     Elast
    0.50
    Activations Density 0.043%

    No Known Activations